{"id":"https://openalex.org/W4408355279","doi":"https://doi.org/10.1109/icassp49660.2025.10888774","title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","display_name":"Scaling A Simple Approach to Zero-Shot Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355279","doi":"https://doi.org/10.1109/icassp49660.2025.10888774"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100531552","display_name":"Jinming Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jinming Zhao","raw_affiliation_strings":["Monash University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Melbourne,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vineel Pratap","raw_affiliation_strings":["Meta Fair,Menlo Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Fair,Menlo Park,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Meta Fair,Menlo Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Fair,Menlo Park,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0351,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96253574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6442705392837524},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.637170135974884},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6302667856216431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6020597219467163},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5746124982833862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3340253233909607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14249694347381592}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442705392837524},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.637170135974884},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6302667856216431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6020597219467163},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5746124982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3340253233909607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14249694347381592},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W273093436","https://openalex.org/W2123798005","https://openalex.org/W2127141656","https://openalex.org/W2804732445","https://openalex.org/W2842511635","https://openalex.org/W2894835365","https://openalex.org/W2953190524","https://openalex.org/W2962799225","https://openalex.org/W2971840980","https://openalex.org/W2972374322","https://openalex.org/W2972706021","https://openalex.org/W3015877095","https://openalex.org/W3035390927","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4285181910","https://openalex.org/W4296069143","https://openalex.org/W4319862635","https://openalex.org/W6620995222","https://openalex.org/W6679237984","https://openalex.org/W6679855610","https://openalex.org/W6691972233","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6795952400","https://openalex.org/W6809739816","https://openalex.org/W6847363464","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W141820298","https://openalex.org/W4403053866","https://openalex.org/W2142393343"],"abstract_inverted_index":{"Despite":[0],"rapid":[1],"progress":[2],"in":[3,82],"increasing":[4],"the":[5,12,48,51,98,113,118,140],"language":[6],"coverage":[7],"of":[8,40,50,89,121],"automatic":[9],"speech":[10],"recognition,":[11],"field":[13],"is":[14,55,124],"still":[15],"far":[16],"from":[17],"covering":[18],"all":[19],"languages":[20,85,110,142],"with":[21,31],"a":[22,32,37,68,104],"known":[23],"writing":[24],"script.":[25],"Recent":[26],"work":[27],"showed":[28],"promising":[29],"results":[30],"zero-shot":[33],"approach":[34,71,123],"requiring":[35],"only":[36,125],"small":[38],"amount":[39],"text":[41],"data,":[42],"however,":[43],"accuracy":[44],"heavily":[45],"depends":[46],"on":[47,73,80],"quality":[49],"used":[52],"phonemizer":[53],"which":[54],"often":[56],"weak":[57],"for":[58,139],"unseen":[59,109],"languages.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"present":[65],"MMS":[66,95,133],"Zero-shot,":[67],"conceptually":[69],"simpler":[70],"based":[72],"romanization":[74],"and":[75],"an":[76],"acoustic":[77],"model":[78],"trained":[79],"data":[81,138],"1,078":[83],"different":[84],"or":[86],"three":[87],"orders":[88],"magnitude":[90],"more":[91],"than":[92,128],"prior":[93],"art.":[94],"Zero-shot":[96,134],"reduces":[97],"average":[99],"character":[100],"error":[101,119],"rate":[102,120],"by":[103],"relative":[105],"46%":[106],"over":[107],"100":[108],"compared":[111],"to":[112],"best":[114],"previous":[115],"work.":[116],"Moreover,":[117],"our":[122],"2.5x":[126],"higher":[127],"in-domain":[129],"supervised":[130],"baselines,":[131],"while":[132],"uses":[135],"no":[136],"labeled":[137],"evaluation":[141],"at":[143],"all.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}